© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 67734
    Prev
    Next
    INDEX
    Explanations

    Especially

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on standalone numeric tokens (e.g. segment‐length or count markers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     while
    -1.31
     also
    -1.26
     with
    -1.17
     to
    -1.11
     along
    -1.02
     during
    -0.95
    If
    -0.93
     when
    -0.90
     without
    -0.88
     has
    -0.87
    POSITIVE LOGITS
     Especially
    1.68
     especially
    1.64
    Especially
    1.63
    especially
    1.54
     surtout
    1.41
     ESPEC
    1.38
     Ведь
    1.36
    Ведь
    1.34
     vooral
    1.33
     especialmente
    1.31
    Activations Density 0.072%

    No Known Activations